Move absolutify_links function to external file

2 files changed, 19 insertions, 16 deletions

diff --git a/pyblog b/pyblog
index b625f1c7..2f87d0eb 100755
--- a/pyblog
+++ b/pyblog
@@ -638,21 +638,6 @@ def rewrite_title():
                             indexmd.write(line)
 
 
-def absolutify_links(soup, baseurl):
-    """Make links in an article absolute.
-
-    Parameters
-    ----------
-    soup : bs4.BeautifulSoup
-    baseurl : str
-
-    """
-    for tag in soup.find_all(lambda tag: tag.has_attr("href")):
-        tag["href"] = urllib.parse.urljoin(baseurl, tag["href"])
-    for tag in soup.find_all(lambda tag: tag.has_attr("src")):
-        tag["src"] = urllib.parse.urljoin(baseurl, tag["src"])
-
-
 def generate_index_and_feed():
     """Generate index.html and feeds (atom and rss)."""
     # pylint: disable=too-many-statements,attribute-defined-outside-init,invalid-name
@@ -753,7 +738,7 @@ def generate_index_and_feed():
                     for script_tag in article.find_all("script"):
                         tags_to_remove.append(script_tag)
                     # make internal links absolute
-                    absolutify_links(article, entry_url)
+                    utils.absolutify_links(article, entry_url)
                     # remove marked tags
                     for tag in tags_to_remove:
                         tag.extract()
diff --git a/utils/utils.py b/utils/utils.py
index bf3d4fbe..a82c23e6 100644
--- a/utils/utils.py
+++ b/utils/utils.py
@@ -7,6 +7,9 @@ import time
 import datetime
 import dateutil.tz
 
+import bs4
+import urllib.parse
+
 
 @contextmanager
 def init_colorama():
@@ -34,3 +37,18 @@ def current_datetime():
     """
     return datetime.datetime.fromtimestamp(round(time.time()),
                                            dateutil.tz.tzlocal())
+
+
+def absolutify_links(soup, baseurl):
+    """Make links in an article absolute.
+
+    Parameters
+    ----------
+    soup : bs4.BeautifulSoup
+    baseurl : str
+
+    """
+    for tag in soup.find_all(lambda tag: tag.has_attr("href")):
+        tag["href"] = urllib.parse.urljoin(baseurl, tag["href"])
+    for tag in soup.find_all(lambda tag: tag.has_attr("src")):
+        tag["src"] = urllib.parse.urljoin(baseurl, tag["src"])